Advertisement

AUTO3D: Novel View Synthesis Through Unsupervisely Learned Variational Viewpoint and Global 3D Representation

Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 12354)

Abstract

This paper targets on learning-based novel view synthesis from a single or limited 2D images without the pose supervision. In the viewer-centered coordinates, we construct an end-to-end trainable conditional variational framework to disentangle the unsupervisely learned relative-pose/rotation and implicit global 3D representation (shape, texture and the origin of viewer-centered coordinates, etc.). The global appearance of the 3D object is given by several appearance-describing images taken from any number of viewpoints. Our spatial correlation module extracts a global 3D representation from the appearance-describing images in a permutation invariant manner. Our system can achieve implicitly 3D understanding without explicitly 3D reconstruction. With an unsupervisely learned viewer-centered relative-pose/rotation code, the decoder can hallucinate the novel view continuously by sampling the relative-pose in a prior distribution. In various applications, we demonstrate that our model can achieve comparable or even better results than pose/3D model-supervised learning-based novel view synthesis (NVS) methods with any number of input views.

Keywords

Unsupervised novel view synthesis Viewer-centered coordinates Variational viewpoints Global 3D representation 

Notes

Acknowledgments

This work was supported by the Jangsu Youth Programme [grant number SBK2020041180], National Natural Science Foundation of China, Younth Programme [grant number 61705221], the Fundamental Research Funds for the Central Universities [grant number GK2240260006], NIH [NS061841, NS095986], Fanhan Technology, and Hong Kong Government General Research Fund GRF (Ref. No.152202/14E) are greatly appreciated.

Supplementary material

504446_1_En_4_MOESM1_ESM.pdf (371 kb)
Supplementary material 1 (pdf 370 KB)

References

  1. 1.
    Alemi, A.A., Fischer, I., Dillon, J.V., Murphy, K.: Deep variational information bottleneck. arXiv preprint arXiv:1612.00410 (2016)
  2. 2.
    Barron, J.T., Malik, J.: Shape, illumination, and reflectance from shading. IEEE Trans. Pattern Anal. Mach. Intell. 37(8), 1670–1687 (2014)CrossRefGoogle Scholar
  3. 3.
    Buades, A., Coll, B., Morel, J.M.: A non-local algorithm for image denoising. In: IEEE Computer Society Conference on Computer Vision and Pattern Recognition, CVPR 2005, vol. 2, pp. 60–65. IEEE (2005)Google Scholar
  4. 4.
    Cao, J., Hu, Y., Yu, B., He, R., Sun, Z.: Load balanced GANs for multi-view face image synthesis. arXiv preprint arXiv:1802.07447 (2018)
  5. 5.
    Chang, A.X., et al.: ShapeNet: an information-rich 3D model repository. arXiv preprint arXiv:1512.03012 (2015)
  6. 6.
    Che, T., et al.: Deep verifier networks: Verification of deep discriminative models with deep generative models. arXiv preprint arXiv:1911.07421 (2019)
  7. 7.
    Chen, X., Song, J., Hilliges, O.: Monocular neural image based rendering with continuous view control. In: Proceedings of the IEEE International Conference on Computer Vision. pp. 4090–4100 (2019)Google Scholar
  8. 8.
    Choy, C.B., Xu, D., Gwak, J.Y., Chen, K., Savarese, S.: 3D-R2N2: a unified approach for single and multi-view 3D object reconstruction. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9912, pp. 628–644. Springer, Cham (2016).  https://doi.org/10.1007/978-3-319-46484-8_38CrossRefGoogle Scholar
  9. 9.
    Chung, F.R., Graham, F.C.: Spectral Graph Theory. No. 92. American Mathematical Soc. (1997)Google Scholar
  10. 10.
    Dosovitskiy, A., Springenberg, J.T., Tatarchenko, M., Brox, T.: Learning to generate chairs, tables and cars with convolutional networks. IEEE Trans. Pattern Anal. Mach. Intell. 39(4), 692–705 (2016)Google Scholar
  11. 11.
    Dosovitskiy, A., Tobias Springenberg, J., Brox, T.: Learning to generate chairs with convolutional neural networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1538–1546 (2015)Google Scholar
  12. 12.
    Du, Q., Gunzburger, M., Lehoucq, R.B., Zhou, K.: Analysis and approximation of nonlocal diffusion problems with volume constraints. SIAM Rev. 54(4), 667–696 (2012)MathSciNetCrossRefGoogle Scholar
  13. 13.
    Feng, Y., Wu, F., Shao, X., Wang, Y., Zhou, X.: Joint 3D face reconstruction and dense alignment with position map regression network. In: Proceedings of the European Conference on Computer Vision (ECCV), pp. 534–551 (2018)Google Scholar
  14. 14.
    Flynn, J., Neulander, I., Philbin, J., Snavely, N.: DeepStereo: learning to predict new views from the world’s imagery. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 5515–5524 (2016)Google Scholar
  15. 15.
    Forsyth, D.A., Ponce, J.: Computer Vision: A Modern Approach. Prentice Hall Professional Technical Reference (2002)Google Scholar
  16. 16.
    Garg, R., B.G., V.K., Carneiro, G., Reid, I.: Unsupervised CNN for single view depth estimation: geometry to the rescue. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9912, pp. 740–756. Springer, Cham (2016).  https://doi.org/10.1007/978-3-319-46484-8_45CrossRefGoogle Scholar
  17. 17.
    Gilboa, G., Osher, S.: Nonlocal linear image regularization and supervised segmentation. Multisc. Model. Simul. 6(2), 595–630 (2007)MathSciNetCrossRefGoogle Scholar
  18. 18.
    Goodfellow, I.: Nips 2016 tutorial: generative adversarial networks. arXiv preprint arXiv:1701.00160 (2016)
  19. 19.
    Goodfellow, I., Bengio, Y., Courville, A.: Deep Learning. MIT Press, Cambridge (2016)zbMATHGoogle Scholar
  20. 20.
    Goodfellow, I., et al.: Generative adversarial nets. In: Advances in neural information processing systems, pp. 2672–2680 (2014)Google Scholar
  21. 21.
    Han, Y., et al.: Wasserstein loss-based deep object detection. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, pp. 998–999 (2020)Google Scholar
  22. 22.
    He, G., Liu, X., Fan, F., You, J.: Classification-aware semi-supervised domain adaptation. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, pp. 964–965 (2020)Google Scholar
  23. 23.
    He, G., Liu, X., Fan, F., You, J.: Image2Audio: facilitating semi-supervised audio emotion recognition with facial expression image. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, pp. 912–913 (2020)Google Scholar
  24. 24.
    Henderson, P., Ferrari, V.: Learning single-image 3D reconstruction by generative modelling of shape, pose and shading. Int. J. Comput. Vis. 1–20 (2019)Google Scholar
  25. 25.
    Higgins, I., et al.: beta-vae: Learning basic visual concepts with a constrained variational framework. In: ICLR, vol. 2, no. 5, p. 6 (2017)Google Scholar
  26. 26.
    Huang, H., He, R., Sun, Z., Tan, T., et al.: IntroVAE: introspective variational autoencoders for photographic image synthesis. In: Advances in Neural Information Processing Systems, pp. 52–63 (2018)Google Scholar
  27. 27.
    Huang, X., Belongie, S.: Arbitrary style transfer in real-time with adaptive instance normalization. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 1501–1510 (2017)Google Scholar
  28. 28.
    Insafutdinov, E., Dosovitskiy, A.: Unsupervised learning of shape and pose with differentiable point clouds. In: Advances in Neural Information Processing Systems, pp. 2802–2812 (2018)Google Scholar
  29. 29.
    Isola, P., Zhu, J.Y., Zhou, T., Efros, A.A.: Image-to-image translation with conditional adversarial networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1125–1134 (2017)Google Scholar
  30. 30.
    Ji, D., Kwon, J., McFarland, M., Savarese, S.: Deep view morphing. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2155–2163 (2017)Google Scholar
  31. 31.
    Kanazawa, A., Tulsiani, S., Efros, A.A., Malik, J.: Learning category-specific mesh reconstruction from image collections. In: Proceedings of the European Conference on Computer Vision (ECCV), pp. 371–386 (2018)Google Scholar
  32. 32.
    Kholgade, N., Simon, T., Efros, A., Sheikh, Y.: 3D object manipulation in a single photograph using stock 3D models. ACM Trans. Graph. (TOG) 33(4), 1–12 (2014)CrossRefGoogle Scholar
  33. 33.
    Kingma, D.P., Ba, J.: Adam: a method for stochastic optimization. arXiv preprint arXiv:1412.6980 (2014)
  34. 34.
    Kingma, D.P., Salimans, T., Jozefowicz, R., Chen, X., Sutskever, I., Welling, M.: Improved variational inference with inverse autoregressive flow. In: Advances in Neural Information Processing Systems, pp. 4743–4751 (2016)Google Scholar
  35. 35.
    Koestinger, M., Wohlhart, P., Roth, P.M., Bischof, H.: Annotated facial landmarks in the wild: a large-scale, real-world database for facial landmark localization. In: 2011 IEEE International Conference on Computer Vision Workshops (ICCV Workshops), pp. 2144–2151. IEEE (2011)Google Scholar
  36. 36.
    Larsen, A.B.L., Sønderby, S.K., Larochelle, H., Winther, O.: Autoencoding beyond pixels using a learned similarity metric. In: ICML (2016)Google Scholar
  37. 37.
    Lin, C.H., Kong, C., Lucey, S.: Learning efficient point cloud generation for dense 3D object reconstruction. In: Thirty-Second AAAI Conference on Artificial Intelligence (2018)Google Scholar
  38. 38.
    Liu, M.Y., Breuel, T., Kautz, J.: Unsupervised image-to-image translation networks. In: Advances in Neural Information Processing Systems, pp. 700–708 (2017)Google Scholar
  39. 39.
    Liu, R., et al.: An intriguing failing of convolutional neural networks and the CoordConv solution. In: Advances in Neural Information Processing Systems, pp. 9605–9616 (2018)Google Scholar
  40. 40.
    Liu, X.: Disentanglement for discriminative visual recognition. arXiv preprint arXiv:2006.07810 (2020)
  41. 41.
    Liu, X., B.V.K., K., Yang, C., Tang, Q., You, J.: Dependency-aware attention control for unconstrained face recognition with image sets. In: European Conference on Computer Vision (2018)Google Scholar
  42. 42.
    Liu, X., Fan, F., Kong, L., Diao, Z., Xie, W., Lu, J., You, J.: Unimodal regularized neuron stick-breaking for ordinal classification. Neurocomputing (2020)Google Scholar
  43. 43.
    Liu, X., Ge, Y., Yang, C., Jia, P.: Adaptive metric learning with deep neural networks for video-based facial expression recognition. J. Electron. Imaging 27(1), 013022 (2018)CrossRefGoogle Scholar
  44. 44.
    Liu, X., Guo, Z., Jia, J., Kumar, B.: Dependency-aware attention control for imageset-based face recognition. In: IEEE Transactions on Information Forensics and Security (2019)Google Scholar
  45. 45.
    Liu, X., Guo, Z., Li, S., Kong, L., Jia, P., You, J., Kumar, B.V.: Permutation-invariant feature restructuring for correlation-aware image set-based recognition. In: The IEEE International Conference on Computer Vision (ICCV), October 2019Google Scholar
  46. 46.
    Liu, X., et al.: Importance-aware semantic segmentation in self-driving with discrete wasserstein training. In: AAAI, pp. 11629–11636 (2020)Google Scholar
  47. 47.
    Liu, X., Ji, W., You, J., Fakhri, G.E., Woo, J.: Severity-aware semantic segmentation with reinforced wasserstein training. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 12566–12575 (2020)Google Scholar
  48. 48.
    Liu, X., Kong, L., Diao, Z., Jia, P.: Line-scan system for continuous hand authentication. Opt. Eng. 56(3), 033106 (2017)CrossRefGoogle Scholar
  49. 49.
    Liu, X., Kumar, B.V., Ge, Y., Yang, C., You, J., Jia, P.: Normalized face image generation with perceptron generative adversarial networks. In: 2018 IEEE 4th International Conference on Identity, Security, and Behavior Analysis (ISBA), pp. 1–8 (2018)Google Scholar
  50. 50.
    Liu, X., Kumar, B.V., Jia, P., You, J.: Hard negative generation for identity-disentangled facial expression recognition. Pattern Recogn. 88, 1–12 (2019)CrossRefGoogle Scholar
  51. 51.
    Liu, X., Li, S., Kong, L., Xie, W., Jia, P., You, J., Kumar, B.: Feature-level Frankenstein: eliminating variations for discriminative recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 637–646 (2019)Google Scholar
  52. 52.
    Liu, X., Vijaya Kumar, B., You, J., Jia, P.: Adaptive deep metric learning for identity-aware facial expression recognition. In: CVPR Workshops, pp. 20–29 (2017)Google Scholar
  53. 53.
    Liu, X., et al.: Conservative wasserstein training for pose estimation. In: The IEEE International Conference on Computer Vision (ICCV), October 2019Google Scholar
  54. 54.
    Liu, X., et al.: Data augmentation via latent space interpolation for image classification. In: 24th International Conference on Pattern Recognition (ICPR), pp. 728–733 (2018)Google Scholar
  55. 55.
    Liu, X., Zou, Y., Song, Y., Yang, C., You, J., K Vijaya Kumar, B.: Ordinal regression with neuron stick-breaking for medical diagnosis. In: Proceedings of the European Conference on Computer Vision (ECCV) (2018)Google Scholar
  56. 56.
    Mathieu, M.F., Zhao, J.J., Zhao, J., Ramesh, A., Sprechmann, P., LeCun, Y.: Disentangling factors of variation in deep representation using adversarial training. In: Advances in Neural Information Processing Systems, pp. 5040–5048 (2016)Google Scholar
  57. 57.
    Nguyen-Phuoc, T., Li, C., Theis, L., Richardt, C., Yang, Y.L.: HoloGAN: unsupervised learning of 3D representations from natural images. arXiv preprint arXiv:1904.01326 (2019)
  58. 58.
    Nguyen-Phuoc, T.H., Li, C., Balaban, S., Yang, Y.: RenderNet: a deep convolutional network for differentiable rendering from 3D shapes. In: Advances in Neural Information Processing Systems, pp. 7891–7901 (2018)Google Scholar
  59. 59.
    Olszewski, K., Tulyakov, S., Woodford, O., Li, H., Luo, L.: Transformable bottleneck networks. arXiv preprint arXiv:1904.06458 (2019)
  60. 60.
    Park, E., Yang, J., Yumer, E., Ceylan, D., Berg, A.C.: Transformation-grounded image generation network for novel 3D view synthesis. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 3500–3509 (2017)Google Scholar
  61. 61.
    Paszke, A., et al.: Automatic differentiation in PyTorch (2017)Google Scholar
  62. 62.
    Pontes, J.K., Kong, C., Sridharan, S., Lucey, S., Eriksson, A., Fookes, C.: Image2Mesh: a learning framework for single image 3D reconstruction. In: Jawahar, C.V., Li, H., Mori, G., Schindler, K. (eds.) ACCV 2018. LNCS, vol. 11361, pp. 365–381. Springer, Cham (2019).  https://doi.org/10.1007/978-3-030-20887-5_23CrossRefGoogle Scholar
  63. 63.
    Rajeswar, S., Mannan, F., Golemo, F., Vazquez, D., Nowrouzezahrai, D., Courville, A.: Pix2Scene: learning implicit 3D representations from images (2018)Google Scholar
  64. 64.
    Rematas, K., Nguyen, C.H., Ritschel, T., Fritz, M., Tuytelaars, T.: Novel views of objects from a single image. IEEE Trans. Pattern Anal. Mach. Intell. 39(8), 1576–1590 (2016)CrossRefGoogle Scholar
  65. 65.
    Saxe, A.M., et al.: On the information bottleneck theory of deep learning (2018)Google Scholar
  66. 66.
    Shin, D., Fowlkes, C.C., Hoiem, D.: Pixels, voxels, and views: A study of shape representations for single view 3D object shape prediction. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 3061–3069 (2018)Google Scholar
  67. 67.
    Sturm, P., Triggs, B.: A factorization based algorithm for multi-image projective structure and motion. In: Buxton, B., Cipolla, R. (eds.) ECCV 1996. LNCS, vol. 1065, pp. 709–720. Springer, Heidelberg (1996).  https://doi.org/10.1007/3-540-61123-1_183CrossRefGoogle Scholar
  68. 68.
    Sun, S.H., Huh, M., Liao, Y.H., Zhang, N., Lim, J.J.: Multi-view to novel view: synthesizing novel views with self-learned confidence. In: Proceedings of the European Conference on Computer Vision (ECCV), pp. 155–171 (2018)Google Scholar
  69. 69.
    Szabó, A., Favaro, P.: Unsupervised 3D shape learning from image collections in the wild. arXiv preprint arXiv:1811.10519 (2018)
  70. 70.
    Tao, Y., Sun, Q., Du, Q., Liu, W.: Nonlocal neural networks, nonlocal diffusion and nonlocal modeling. arXiv preprint arXiv:1806.00681 (2018)
  71. 71.
    Tatarchenko, M., Dosovitskiy, A., Brox, T.: Multi-view 3D models from single images with a convolutional network. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9911, pp. 322–337. Springer, Cham (2016).  https://doi.org/10.1007/978-3-319-46478-7_20CrossRefGoogle Scholar
  72. 72.
    Tian, Y., Peng, X., Zhao, L., Zhang, S., Metaxas, D.N.: CR-GAN: learning complete representations for multi-view generation. arXiv preprint arXiv:1806.11191 (2018)
  73. 73.
    Tran, L., Yin, X., Liu, X.: Disentangled representation learning GAN for pose-invariant face recognition. In: CVPR, vol. 3, p. 7 (2017)Google Scholar
  74. 74.
    Vaswani, A., et al.: Attention is all you need. In: Advances in Neural Information Processing Systems, pp. 5998–6008 (2017)Google Scholar
  75. 75.
    Wang, X., Girshick, R., Gupta, A., He, K.: Non-local neural networks. In: The IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2018)Google Scholar
  76. 76.
    Wang, Z., Bovik, A.C., Sheikh, H.R., Simoncelli, E.P., et al.: Image quality assessment: from error visibility to structural similarity. IEEE Trans. Image Process. 13(4), 600–612 (2004)CrossRefGoogle Scholar
  77. 77.
    Wu, J., Zhang, C., Zhang, X., Zhang, Z., Freeman, W.T., Tenenbaum, J.B.: Learning shape priors for single-view 3D completion and reconstruction. In: Proceedings of the European Conference on Computer Vision (ECCV), pp. 646–662 (2018)Google Scholar
  78. 78.
    Xie, J., Girshick, R., Farhadi, A.: Deep3D: fully automatic 2D-to-3D video conversion with deep convolutional neural networks. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9908, pp. 842–857. Springer, Cham (2016).  https://doi.org/10.1007/978-3-319-46493-0_51CrossRefGoogle Scholar
  79. 79.
    Xu, X., Chen, Y.C., Jia, J.: View independent generative adversarial network for novel view synthesis. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 7791–7800 (2019)Google Scholar
  80. 80.
    Yang, C., Liu, X., Tang, Q., Kuo, C.C.J.: Towards disentangled representations for human retargeting by multi-view learning. arXiv preprint arXiv:1912.06265 (2019)
  81. 81.
    Yang, C., Song, Y., Liu, X., Tang, Q., Kuo, C.C.J.: Image inpainting using block-wise procedural training with annealed adversarial counterpart. arXiv preprint arXiv:1803.08943 (2018)
  82. 82.
    Zakharov, E., Shysheya, A., Burkov, E., Lempitsky, V.: Few-shot adversarial learning of realistic neural talking head models. arXiv preprint arXiv:1905.08233 (2019)
  83. 83.
    Zhang, X., Zhang, Z., Zhang, C., Tenenbaum, J., Freeman, B., Wu, J.: Learning to reconstruct shapes from unseen classes. In: Advances in Neural Information Processing Systems, pp. 2257–2268 (2018)Google Scholar
  84. 84.
    Zhou, B., Andonian, A., Torralba, A.: Temporal relational reasoning in videos. In ECCV (2018)Google Scholar
  85. 85.
    Zhou, T., Tulsiani, S., Sun, W., Malik, J., Efros, A.A.: View synthesis by appearance flow. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9908, pp. 286–301. Springer, Cham (2016).  https://doi.org/10.1007/978-3-319-46493-0_18CrossRefGoogle Scholar
  86. 86.
    Zhu, J.Y., Park, T., Isola, P., Efros, A.A.: Unpaired image-to-image translation using cycle-consistent adversarial networks. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 2223–2232 (2017)Google Scholar
  87. 87.
    Zhu, X., Lei, Z., Liu, X., Shi, H., Li, S.Z.: Face alignment across large poses: a 3D solution. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 146–155 (2016)Google Scholar

Copyright information

© Springer Nature Switzerland AG 2020

Authors and Affiliations

  1. 1.HMS, Harvard UniversityBostonUSA
  2. 2.MILAUniversité de MontréalMontréalCanada
  3. 3.Nanjing University of Information Science and TechnologyNanjingChina
  4. 4.Fanhan Tech. Inc.SuzhouChina
  5. 5.Facebook AIBostonUSA
  6. 6.Carnegie Mellon UniversityPittsburghUSA
  7. 7.Department of ComputingThe Hong Kong Polytechnic UniversityHung HomHong Kong

Personalised recommendations